Weak Disambiguation for Partial Structured Output Learning
- URL: http://arxiv.org/abs/2209.09410v1
- Date: Tue, 20 Sep 2022 02:12:31 GMT
- Title: Weak Disambiguation for Partial Structured Output Learning
- Authors: Xiaolei Lu, Tommy W.S.Chow
- Abstract summary: We propose a novel weak disambiguation for partial structured output learning (WD-PSL)
Each candidate label is assigned with a confidence value indicating how likely it is the true label.
The experimental results on several sequence labeling tasks of Natural Language Processing show the effectiveness of the proposed model.
- Score: 8.239028141030621
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Existing disambiguation strategies for partial structured output learning
just cannot generalize well to solve the problem that there are some candidates
which can be false positive or similar to the ground-truth label. In this
paper, we propose a novel weak disambiguation for partial structured output
learning (WD-PSL). First, a piecewise large margin formulation is generalized
to partial structured output learning, which effectively avoids handling large
number of candidate structured outputs for complex structures. Second, in the
proposed weak disambiguation strategy, each candidate label is assigned with a
confidence value indicating how likely it is the true label, which aims to
reduce the negative effects of wrong ground-truth label assignment in the
learning process. Then two large margins are formulated to combine two types of
constraints which are the disambiguation between candidates and non-candidates,
and the weak disambiguation for candidates. In the framework of alternating
optimization, a new 2n-slack variables cutting plane algorithm is developed to
accelerate each iteration of optimization. The experimental results on several
sequence labeling tasks of Natural Language Processing show the effectiveness
of the proposed model.
Related papers
- Constrained Decoding for Fill-in-the-Middle Code Language Models via Efficient Left and Right Quotienting of Context-Sensitive Grammars [11.279507894576213]
This paper contributes an incremental synthesis that allows early rejection of syntactically incorrect code.
We extend the Earley parsing algorithm to allow for left and right quotients of context-free grammars.
arXiv Detail & Related papers (2024-02-28T02:12:47Z) - Understanding and Mitigating Classification Errors Through Interpretable
Token Patterns [58.91023283103762]
Characterizing errors in easily interpretable terms gives insight into whether a classifier is prone to making systematic errors.
We propose to discover those patterns of tokens that distinguish correct and erroneous predictions.
We show that our method, Premise, performs well in practice.
arXiv Detail & Related papers (2023-11-18T00:24:26Z) - Robust Representation Learning for Unreliable Partial Label Learning [86.909511808373]
Partial Label Learning (PLL) is a type of weakly supervised learning where each training instance is assigned a set of candidate labels, but only one label is the ground-truth.
This is known as Unreliable Partial Label Learning (UPLL) that introduces an additional complexity due to the inherent unreliability and ambiguity of partial labels.
We propose the Unreliability-Robust Representation Learning framework (URRL) that leverages unreliability-robust contrastive learning to help the model fortify against unreliable partial labels effectively.
arXiv Detail & Related papers (2023-08-31T13:37:28Z) - Unreliable Partial Label Learning with Recursive Separation [44.901941653899264]
Unreliable Partial Label Learning (UPLL) is proposed, in which the true label may not be in the candidate label set.
We propose a two-stage framework named Unreliable Partial Label Learning with Recursive Separation (UPLLRS)
Our method demonstrates state-of-the-art performance as evidenced by experimental results.
arXiv Detail & Related papers (2023-02-20T10:39:31Z) - Meta Objective Guided Disambiguation for Partial Label Learning [44.05801303440139]
We propose a novel framework for partial label learning with meta objective guided disambiguation (MoGD)
MoGD aims to recover the ground-truth label from candidate labels set by solving a meta objective on a small validation set.
The proposed method can be easily implemented by using various deep networks with the ordinary SGD.
arXiv Detail & Related papers (2022-08-26T06:48:01Z) - Single-channel speech separation using Soft-minimum Permutation
Invariant Training [60.99112031408449]
A long-lasting problem in supervised speech separation is finding the correct label for each separated speech signal.
Permutation Invariant Training (PIT) has been shown to be a promising solution in handling the label ambiguity problem.
In this work, we propose a probabilistic optimization framework to address the inefficiency of PIT in finding the best output-label assignment.
arXiv Detail & Related papers (2021-11-16T17:25:05Z) - Reducing Confusion in Active Learning for Part-Of-Speech Tagging [100.08742107682264]
Active learning (AL) uses a data selection algorithm to select useful training samples to minimize annotation cost.
We study the problem of selecting instances which maximally reduce the confusion between particular pairs of output tags.
Our proposed AL strategy outperforms other AL strategies by a significant margin.
arXiv Detail & Related papers (2020-11-02T06:24:58Z) - Pseudo-Convolutional Policy Gradient for Sequence-to-Sequence
Lip-Reading [96.48553941812366]
Lip-reading aims to infer the speech content from the lip movement sequence.
Traditional learning process of seq2seq models suffers from two problems.
We propose a novel pseudo-convolutional policy gradient (PCPG) based method to address these two problems.
arXiv Detail & Related papers (2020-03-09T09:12:26Z) - Progressive Identification of True Labels for Partial-Label Learning [112.94467491335611]
Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label.
Most existing methods elaborately designed as constrained optimizations that must be solved in specific manners, making their computational complexity a bottleneck for scaling up to big data.
This paper proposes a novel framework of classifier with flexibility on the model and optimization algorithm.
arXiv Detail & Related papers (2020-02-19T08:35:15Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.